{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.22810551524162292, "min": 0.22018039226531982, "max": 1.4481186866760254, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 6839.515625, "min": 6587.79736328125, "max": 43930.12890625, "count": 50 }, "Pyramids.Step.mean": { "value": 1499900.0, "min": 29952.0, "max": 1499900.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499900.0, "min": 29952.0, "max": 1499900.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7367997169494629, "min": -0.1058138757944107, "max": 0.7533698081970215, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 216.61912536621094, "min": -25.39533042907715, "max": 222.99746704101562, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025196237489581108, "min": -0.014034638181328773, "max": 0.33072778582572937, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.407693862915039, "min": -3.7051444053649902, "max": 78.38248443603516, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06929936935340579, "min": 0.065273526918775, "max": 0.0736978821301212, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.970191170947681, "min": 0.48577950736935965, "max": 1.1054682319518179, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016834301545706327, "min": 0.0003710021738533183, "max": 0.019542735297277215, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23568022163988855, "min": 0.0029680173908265464, "max": 0.27359829416188103, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.0882989706000005e-06, "min": 3.0882989706000005e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.3236185588400006e-05, "min": 4.3236185588400006e-05, "max": 0.003401904466031933, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1010294, "min": 0.1010294, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4144116, "min": 1.3794090666666667, "max": 2.5651288666666665, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011283706000000004, "min": 0.00011283706000000004, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015797188400000005, "min": 0.0015797188400000005, "max": 0.11342340985999999, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008865910582244396, "min": 0.007768879644572735, "max": 0.40094178915023804, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1241227462887764, "min": 0.10876431316137314, "max": 2.8065924644470215, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 243.7094017094017, "min": 243.7094017094017, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28514.0, "min": 15984.0, "max": 32915.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.756290581363898, "min": -1.0000000521540642, "max": 1.756290581363898, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.48599801957607, "min": -32.000001668930054, "max": 205.48599801957607, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.756290581363898, "min": -1.0000000521540642, "max": 1.756290581363898, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.48599801957607, "min": -32.000001668930054, "max": 205.48599801957607, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02240621386497365, "min": 0.02240621386497365, "max": 7.940638515166938, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.621527022201917, "min": 2.4750754179622163, "max": 127.05021624267101, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1760282411", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/py310/lib/python3.10/site-packages/mlagents/trainers/learn.py ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training --no-graphics --force", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1760286343" }, "total": 3932.445077505, "count": 1, "self": 0.5316384190000463, "children": { "run_training.setup": { "total": 0.019649589999971795, "count": 1, "self": 0.019649589999971795 }, "TrainerController.start_learning": { "total": 3931.893789496, "count": 1, "self": 2.747863139044057, "children": { "TrainerController._reset_env": { "total": 2.2075166980002905, "count": 1, "self": 2.2075166980002905 }, "TrainerController.advance": { "total": 3926.8596448929566, "count": 96461, "self": 2.8434670200631444, "children": { "env_step": { "total": 2860.962575956028, "count": 96461, "self": 2580.199533646931, "children": { "SubprocessEnvManager._take_step": { "total": 279.11620963702717, "count": 96461, "self": 8.109727121950527, "children": { "TorchPolicy.evaluate": { "total": 271.00648251507664, "count": 93808, "self": 271.00648251507664 } } }, "workers": { "total": 1.6468326720701043, "count": 96461, "self": 0.0, "children": { "worker_root": { "total": 3924.3982057779376, "count": 96461, "is_parallel": true, "self": 1547.272958242836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020191139997223218, "count": 1, "is_parallel": true, "self": 0.0006612319998566818, "children": { "_process_rank_one_or_two_observation": { "total": 0.00135788199986564, "count": 8, "is_parallel": true, "self": 0.00135788199986564 } } }, "UnityEnvironment.step": { "total": 0.05442911999989519, "count": 1, "is_parallel": true, "self": 0.0005193939996388508, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004889159999947879, "count": 1, "is_parallel": true, "self": 0.0004889159999947879 }, "communicator.exchange": { "total": 0.05158887700008563, "count": 1, "is_parallel": true, "self": 0.05158887700008563 }, "steps_from_proto": { "total": 0.0018319330001759226, "count": 1, "is_parallel": true, "self": 0.0005307559999891964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013011770001867262, "count": 8, "is_parallel": true, "self": 0.0013011770001867262 } } } } } } }, "UnityEnvironment.step": { "total": 2377.1252475351016, "count": 96460, "is_parallel": true, "self": 56.56406857896036, "children": { "UnityEnvironment._generate_step_input": { "total": 37.849778398101535, "count": 96460, "is_parallel": true, "self": 37.849778398101535 }, "communicator.exchange": { "total": 2096.6187504830623, "count": 96460, "is_parallel": true, "self": 2096.6187504830623 }, "steps_from_proto": { "total": 186.09265007497743, "count": 96460, "is_parallel": true, "self": 41.88365706271907, "children": { "_process_rank_one_or_two_observation": { "total": 144.20899301225836, "count": 771680, "is_parallel": true, "self": 144.20899301225836 } } } } } } } } } } }, "trainer_advance": { "total": 1063.0536019168653, "count": 96461, "self": 5.438706842788633, "children": { "process_trajectory": { "total": 211.86330230909607, "count": 96461, "self": 211.55280429909544, "children": { "RLTrainer._checkpoint": { "total": 0.3104980100006287, "count": 3, "self": 0.3104980100006287 } } }, "_update_policy": { "total": 845.7515927649806, "count": 673, "self": 461.6912215150046, "children": { "TorchPPOOptimizer.update": { "total": 384.060371249976, "count": 34266, "self": 384.060371249976 } } } } } } }, "trainer_threads": { "total": 9.789991963771172e-07, "count": 1, "self": 9.789991963771172e-07 }, "TrainerController._save_models": { "total": 0.07876378699984343, "count": 1, "self": 0.001023535000058473, "children": { "RLTrainer._checkpoint": { "total": 0.07774025199978496, "count": 1, "self": 0.07774025199978496 } } } } } } }